Skip to content

Update quantization file name #78

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
ermanok merged 1 commit into from
Apr 11, 2025
Merged

Update quantization file name #78

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion Guides/MAX78000_Workflow_Guide.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -43,7 +43,7 @@ Quantization is the process of converting floating point weights from a checkpoi

Before working in the synthesis directory, be sure to run _deactivate_ followed by _source bin/activate_ in order to configure the python environment for synthesis.

Continuing with our mnist example, copy the _best.pth.tar_ file from the logs/\<time/date\> directory into the trained directory and rename it to _ai85-mnist-qat8.pth.tar_ (you may need to first delete the pre-existing file of this name). This will allow you to use the existing mnist quantize script, _scripts/quantize\_mnist.sh_ located in the _scripts_ directory.
Continuing with our mnist example, copy the _qat_best.pth.tar_ file from the logs/\<time/date\> directory into the trained directory and rename it to _ai85-mnist-qat8.pth.tar_ (you may need to first delete the pre-existing file of this name). This will allow you to use the existing mnist quantize script, _scripts/quantize\_mnist.sh_ located in the _scripts_ directory.

quantize\_mnist.sh:

Expand Down